Invited Talk by Dr. Anand Mishra:"Understanding Text in Scene Images"
Recognizing scene text is a challenging problem, even more so than the recognition of scanned documents. Given the rapid growth of camera-based applications readily available on obile phones, understanding scene text is more important than ever.One could, for instance, foresee an application to answer questions such as,“What does this sign say?". This is related to the problem of Optical Character Recognition (OCR), which has a long history in the computer vision community. However, the success of OCR systems is largely restricted to text from scanned ocuments. Scene text exhibits a large variability in appearances, and can prove to be challenging even for the state-of-the-art OCR methods. Many scene understanding methods recognize objects and regions like roads, trees,sky in the image successfully, but tend to ignore the text on the sign board.In this talk I will talk about various techniques proposed by us to fill this gap in understanding the scene. Parts of this talk have been appeared at CVPR'12, ICCV'13, BMVC'12 and ICDAR'11 .
Anand Mishra is a PhD from IIIT-Hyderabad , jointly advised by Prof.Jawahar from IIIT-H and Dr. Karteek Alhari from inria-LEAR. His works on scene text understanding have been published at top-tier computer vision venues, and are highly followed by the community. Anand is the recipient of the Microsoft Research India PhD fellowship.Recently, his PhD work has been awarded the First Runner-up for Best Doctoral Dissertation Award by Xerox Research Center India